A predictive model for the passenger demand on a taxi network
; Gama, J.G.
; Damas, L.D.
A predictive model for the passenger demand on a taxi network, Proc IEEE Conf. on Intelligent Transportation Systems, Anchorage, Alaska, United States, Vol. ., pp. . - ., September, 2012.
Digital Object Identifier: 0
In the last decade, the real-time vehicle location systems attracted everyone attention for the new kind of rich spatio-temporal information. The fast processing of this large amount of information is a growing and explosive challenge. Taxi companies are already exploring such information in efficient
taxi dispatching and time-saving route finding. In this paper, we propose a
novel methodology to produce online short term predictions on the passenger
demand spatial distribution over 63 taxi stands in the city of Porto, Portugal.
We did so using time series forecasting techniques to the processed events
constantly communicated for 441 taxi vehicles. Our tests using 4 months
of real data demonstrated that this model is a true major contribution to
the driver mobility intelligence: 76% of the 86411 demanded taxi services
were accurately forecasted in a 30 minutes time horizon.